Abstract
Inspired by human cognition, Jiang et al. 2023 create a benchmark for assessing LLMs’ lateral thinking—thinking outside the box. Building upon this benchmark, we investigate how different prompting methods enhance LLMs’ performance on this task to reveal their inherent power for outside-the-box thinking ability. Through participating in SemEval-2024, task 9, Sentence Puzzle sub-task, we explore prompt engineering methods: chain of thoughts (CoT) and direct prompting, enhancing with informative descriptions, and employing contextualizing prompts using a retrieval augmented generation (RAG) pipeline. Our experiments involve three LLMs including GPT-3.5, GPT-4, and Zephyr-7B-beta. We generate a dataset of thinking paths between riddles and options using GPT-4, validated by humans for quality. Findings indicate that compressed informative prompts enhance performance. Dynamic in-context learning enhances model performance significantly. Furthermore, fine-tuning Zephyr on our dataset enhances performance across other commonsense datasets, underscoring the value of innovative thinking.- Anthology ID:
- 2024.semeval-1.251
- Volume:
- Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024)
- Month:
- June
- Year:
- 2024
- Address:
- Mexico City, Mexico
- Editors:
- Atul Kr. Ojha, A. Seza Doğruöz, Harish Tayyar Madabushi, Giovanni Da San Martino, Sara Rosenthal, Aiala Rosá
- Venue:
- SemEval
- SIG:
- SIGLEX
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1767–1778
- Language:
- URL:
- https://aclanthology.org/2024.semeval-1.251
- DOI:
- 10.18653/v1/2024.semeval-1.251
- Cite (ACL):
- Pouya Sadeghi, Amirhossein Abaskohi, and Yadollah Yaghoobzadeh. 2024. uTeBC-NLP at SemEval-2024 Task 9: Can LLMs be Lateral Thinkers?. In Proceedings of the 18th International Workshop on Semantic Evaluation (SemEval-2024), pages 1767–1778, Mexico City, Mexico. Association for Computational Linguistics.
- Cite (Informal):
- uTeBC-NLP at SemEval-2024 Task 9: Can LLMs be Lateral Thinkers? (Sadeghi et al., SemEval 2024)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2024.semeval-1.251.pdf